GEE Inference for KK Designs with Binary Response

Fits a Generalized Estimating Equations (GEE) model with a binomial family and logit link, \(\mathrm{logit}\,\Pr(Y_i = 1 \mid x_i) = x_i^\top\beta\), for binary (incidence) responses under a KK matching-on-the-fly design, using an exchangeable working correlation structure where each cluster is either a matched pair (2 members) or a reservoir singleton (1 member) — see $compute_estimate()'s method-level documentation for the full fitting contract (internal Rcpp solver vs. geepack fallback, hardening/retry behavior). GEE is used here purely to fit one marginal model jointly across matched-pair and reservoir subjects while accounting for the within-pair correlation the matching induces, not as a longitudinal/repeated-measures tool. Inference is quasi-likelihood/estimating-equation based (likelihood_tier = "quasi"): standard errors are GEE sandwich (robust) standard errors, not model-likelihood-based.

References

Liang, K.-Y., and Zeger, S. L. (1986). "Longitudinal Data Analysis Using Generalized Linear Models." Biometrika, 73(1), 13-22, doi:10.1093/biomet/73.1.13 , for the GEE estimating-equation framework and sandwich variance estimator used here.

Super class

Inference -> InferenceIncidKKGEE

Methods

Public methods

• InferenceIncidKKGEE$new()

• InferenceIncidKKGEE$clone()

+ inherited public methods from Inference

• Inference$capabilities()
• Inference$compute_asymp_confidence_interval()
• Inference$compute_asymp_two_sided_pval()
• Inference$compute_estimate()
• Inference$compute_exact_confidence_interval()
• Inference$compute_exact_two_sided_pval_for_treatment_effect()
• Inference$duplicate()
• Inference$get_analysis_data()
• Inference$get_covariates()
• Inference$get_design_object()
• Inference$get_model_formula()
• Inference$get_nonestimable_reason()
• Inference$get_nonestimable_stage()
• Inference$get_optimization_alg()
• Inference$get_response()
• Inference$get_response_type()
• Inference$get_treatment()
• Inference$is_nonestimable()
• Inference$set_optimization_alg()
• Inference$set_seed()
• Inference$supports()

---

InferenceIncidKKGEE$new()

Initialize KK binary-response GEE inference, validate the matched/reservoir design, and prepare the exchangeable-working-correlation binomial (logit-link) GEE fitting machinery used by InferenceIncidKKGEE.

Usage

InferenceIncidKKGEE$new(
  des_obj,
  model_formula = NULL,
  use_rcpp = TRUE,
  verbose = FALSE,
  smart_cold_start_default = NULL
)

Arguments

des_obj

A completed Design object with an incidence response.

model_formula

Optional formula for covariate adjustment.

use_rcpp

Whether to use the internal Rcpp GEE solver (TRUE, default) with automatic fallback to geepack::geeglm on failure, or always use geepack::geeglm directly (FALSE).

verbose

Whether to print progress messages.

smart_cold_start_default

Whether to use smart cold start values.

---

InferenceIncidKKGEE$clone()

The objects of this class are cloneable with this method.

Usage

InferenceIncidKKGEE$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

Examples

# \donttest{
seq_des = DesignSeqOneByOneKK14$new(n = 10, response_type = 'incidence')
for (i in 1:10) {
  seq_des$add_one_subject_to_experiment_and_assign(data.frame(x1 = rnorm(1), x2 = rnorm(1)))
}
seq_des$add_all_subject_responses(rbinom(10, 1, 0.5))
inf = InferenceIncidKKGEE$new(seq_des)
inf$compute_estimate()
#> [1] -0.9805352
# }